© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 10865
    Prev
    Next
    INDEX
    Explanations

    significant phrases and themes related to leadership and transition in organizational contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.13
    1:0.10
    2:0.06
    3:0.04
    4:0.03
    5:0.03
    6:0.19
    7:0.12
    8:0.04
    9:0.05
    10:0.12
    11:0.04
    Negative Logits
     checkpoint
    -2.92
     pes
    -2.75
     Zoro
    -2.69
     Lopez
    -2.69
    Platform
    -2.62
     mysql
    -2.61
    checking
    -2.54
     Citiz
    -2.53
     Romero
    -2.50
     Guatemala
    -2.49
    POSITIVE LOGITS
     Earl
    7.20
    arl
    3.44
     Ear
    3.25
     Marqu
    3.13
     Fitz
    3.03
     Wald
    2.97
     Hunts
    2.90
     Engel
    2.82
     Baron
    2.75
     Kil
    2.74
    Activations Density 0.002%

    No Known Activations